Server facts
Kubernetes MCP Server
Project
- Author
- manusa
- Repository
- github.com/manusa/kubernetes-mcp-server
- License
- Apache-2.0
- Category
- Cloud & DevOps
Tech
- Runtime / language
- goGo
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 2,162
- Last commit
- Data as of
Tags
- Cluster Management
- Go
- Helm
- Kubernetes
- Openshift
Overview
Kubernetes MCP Server connects assistants directly to Kubernetes and OpenShift APIs through a native Go implementation. It is not a command wrapper around kubectl or Helm. The documented capabilities include generic resource operations, pod inspection and logs, resource metrics, command execution in pods, events, namespaces, and OpenShift projects. Helm release management and Tekton-specific execution workflows extend the server beyond basic cluster inspection.
The implementation can use kubeconfig or in-cluster configuration and respond to Kubernetes configuration changes. Multiple clusters can be available at once, with an option to restrict access to the current context. Toolsets let administrators expose only the capabilities needed for a workflow. Read-only mode blocks writes, while another option disables destructive actions. TOML configuration adds controls such as denied resource types, and the documentation points to dedicated production guidance for service accounts and restricted access. These controls matter because the broader feature set includes operations that modify live resources.
Distribution options include native binaries for Linux, macOS, and Windows, npm and Python packages, and containers. The native binary does not require Node.js, Python, or separate cluster command-line tools. Stdio client examples use npx; selecting a port enables network MCP endpoints. Optional OpenTelemetry support provides tracing and metrics, and structured MCP logs redact sensitive values. The supplied README describes the operation families but ends before listing exact individual tool identifiers.
Install & configure
Requirements
- Access to a Kubernetes cluster
- Usable kubeconfig or in-cluster credentials
- Node.js and npm for this npx option
- An MCP-compatible client
npx -y kubernetes-mcp-server@latestThis is the documented Claude Desktop and Cursor launch, without the help-only flag from the input hint. Native binaries do not require Node.js or Python. Review read-only mode, toolsets, and resource restrictions before granting production access.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"kubernetes-mcp-server": {
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
],
"env": {}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"kubernetes-mcp-server": {
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
],
"env": {}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"kubernetes-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
],
"env": {}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"kubernetes-mcp-server": {
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
],
"env": {}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"kubernetes-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kubernetes-mcp-server@latest"
],
"env": {}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
No individual tool names were confirmed in the source material. Check the repository for its current tool list.
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Investigate pod logs, events, and resource consumption with an assistant.
- Inspect Kubernetes and OpenShift resources in read-only mode.
- Manage Helm releases through selected toolsets.
- Start or restart Tekton pipeline and task executions.
- Work across kubeconfig-defined clusters from one MCP connection.
Strengths
- Calls the Kubernetes API directly without kubectl or Helm subprocesses.
- Provides native cross-platform binaries.
- Includes toolset, read-only, and resource-denial controls.
- Supports multiple clusters and OpenShift.
Limitations
- Requires access credentials for a Kubernetes cluster.
- Write-capable operations need deliberate restrictions for production use.
- Exact tool identifiers are not stated in the supplied README excerpt.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
